tacone

For anybody interested, here's the related skill: https://agents.stackoverflow.com/skill.md

I think they tried too hard to structure things and keep everything clean, which becomes difficult or even outright deleterious when the numbers are large.

They should have accepted a certain level of mess instead of being so strict. After all, even good popular answers become outdated sooner or later.

The second opinion advice is gold and something we should always do when the stakes are high.

Not a doctor, that said: beside the surgical operations and medicines, one thing I'd consider adding is the ketogenic diet. Research medical studies and emerging evidence, pro/cons on the internet and seriously consider switching to it.

Depending on your conditions a state of kethosis might prove demanding to your body, but even staying very near to it might probably prove useful.

Noticed they are present in OpenRouter, but Qwen 3.8 is not there yet. Hopefully it'll get there soon.

For those who haven't noticed though, the context size they allow for Qwen is just 128k. Still interesting as a specialized sub-agent but not really well suited for long tasks.

I copy pasted this whole debate in Claude Sonnet 5 (web). The model came up with a summary but the thinking trace was entirely omitted.

Well, if you ask me, that is dangerous.

So it is as "dangerous" as Fable?

Next up: upgrade to Pro to disable memory.

It began when they added ?utm=chatgpt to their links, it's been a while, we've seen it coming.

Possibly related: https://gifcities.org/search?q=dollar&offset=0&page_size=200

Vibecoded a simple YouTube summarizer: https://github.com/tacone/prosey

The code might be slop, but it saves me time extracting information from long-form videos that would require 20-60 minutes of my time otherwise.

Also I get to not feed the algorithm just for the sake of curiosity.

My take is that Anthropic and OpenAI simply are NOT competing on price. 2 big players are often not enough to create tension on price.

Chinese models and open model providers are, indeed, competing on price, and the difference shows.

Looks great, especially on mobile, congrats!

That's actually a good point. I had Fable available almost immediately under my Copilot subscription and never bothered to use it even to say hello.

But from what I hear, Fable looks like an incremental update, with improved behavior imprinted by training.

Something that you could theoretically approximate by using a good set of instructions and model orchestration (tweaking the session life cycle, using a second model to understand user intentions, using a third model to prevent drift, ...).

If the above is true, the only discriminator would be user effort.

If Fable is dangerous, then we are still in danger right now, and have been for the last few months at the very least.

I'm starting to think that what Anthropic really fears is not vulnerability discovery but rather Fable going around the internet making trouble.

That also means people are paying money to execute a prompt they've (partially) written.

What a nightmare, happy you've made it through.

Cancelled my personal subscription (annual) yesterday.

- they "swallowed" my monthly subscription in January, I had to subscribe (and pay again)

- they promised tools to preview the new costs, they did too little and too badly (you have to click an export button, wait for a mail and click on a link on it, then download their csv which even showed substantial dollar costs for rows with 0 requests)

- models kept on appearing/disappearing/re-appearing-disabled on our company account in the latest weeks

- as of May 31th, I had no clue and could not tell if I would been migrated to token billing, or would have to stay with the moronic new multipliers. News came on Jun 1st, of course

They don't really look able or willing to properly manage their own product at the moment. And yes, new subscription are paused, so I won't be able to re-subscribe.

Quite frankly the only reason to go copilot is to have it in the VSCode chat (and yes, there's some chance to use it BYOK, provided it works).

Besides, their offering even at market prices looks inferior to what you can get elsewhere. You can use DeepSeek and pay pennies, use Fireworks and have the choice to use cheaper open models (which GitHub does not provide, and are actually good and even better than Claude sometimes), or subscribe to Open Router and use virtually anything.

I still have no idea if cancelling my subscription will get any money back, probably not.

Well.. I can't, nobody can. Perhaps it was a placebo effect or perhaps I had low levels of creatine and felt the difference. I often felt better right after taking it though, not consistently but often.

The first time I took creatine (6g IIRC), I actually felt the mental effect just 2 minutes later. A pleasurable sensation of augmented presence and (mental) relaxation.

I paused taking that momentarily out of precaution while I wait some physical issue to normalize, but I plan to resume it in some weeks. Also it is considered a very safe supplement.

Just spent an hour trying to make it work (including re-compiling) with the jsruntime.

`Error: JavaScript modules found but libperry_jsruntime.a not found. Build it with: cargo build --release -p perry-jsruntime`

Turns out jsruntime was removed one week ago, but the error messages probably not have been updated as they should.

https://github.com/PerryTS/perry/commit/848339fa4ee4b00a53f5...

I don't really understand why the comment has been downvoted.

We actually need more of this, perhaps not in this exact shape, but similar.

It would be extremely cool to be able to write one or two lines of prompt in my harness, and have a light model iterate with me a few times writing/proposing requirements, guidelines and explanations, refining the prompt until it's ready to be sent to the actual LLM.

Lack of specifications in the prompt is (imho?) one of the main drivers that lead the LLMs astray, and it often happens because it's not realistic to always type or even thing every angle before submitting each prompt.

Think of it as the missing link between a single-shot prompt and a skill.

It should be ideally integrated in the chat, for quick access.

This project is probably different in aim, but I still find it interesting.

Doesn't compaction invalidate token caching, btw?

TIL I might be able to use DeepSeek directly from VS Copilot https://github.com/Vizards/deepseek-v4-for-copilot (disclaimer: I have to try it yet).

I am looking for something similar. Any tutorial or resource on how to set up things?

I was looking exactly for something like that. I tried installing the Linux version and it runs but:

1. it's behind a login wall | 2. tries to download its own OpenCode instead of using the one installed on my machine

I also tried to create a new workspace. It asked what I want to do. I tried with "create user accounts", and it proceeded to create the git worktree (without asking for its name) and sent that prompt straight to OpenCode without allowing me to choose the LLM model.

I plaud the effort - I really do - but it doesn't really seems a great experience for now.

It's also dealing with memory issues (see: Memory Megathread https://github.com/anomalyco/opencode/issues/20695).

And in my experience is not that much faster to start than more complex software like Visual Studio Code.

Because most often their real purpose is to stand out in a powerpoint presentation.